Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific books or book series

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lication
    -0.87
    enegger
    -0.79
    sed
    -0.78
    eli
    -0.75
    utical
    -0.75
    resent
    -0.73
    hement
    -0.72
    ptive
    -0.72
    onse
    -0.70
     pleased
    -0.69
    POSITIVE LOGITS
     Souls
    0.92
    pedia
    0.89
     Continent
    0.87
     Lives
    0.81
     Voy
    0.80
     Vikings
    0.78
     Abbey
    0.77
     Ones
    0.76
     Worlds
    0.76
     Testament
    0.74
    Act Density 0.039%

    No Known Activations